Get compressed dependency context for an ABAP object. Returns only the public API contracts (method signatures, interface definitions, type declarations) of all objects that the target depends on — NOT the full source code. This is the most token-efficient way to understand dependencies. Instead ...
Part of the Arc 1 server.
Free to start. No card required.
AI agents call SAPContext to retrieve information from Arc 1 without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though SAPContext only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"SAPContext": {}
}
}See the full Arc 1 policy for all 11 tools.
These attack patterns abuse exactly the kind of access SAPContext gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Get compressed dependency context for an ABAP object. Returns only the public API contracts (method signatures, interface definitions, type declarations) of all objects that the target depends on — NOT the full source code. This is the most token-efficient way to understand dependencies. Instead of N separate SAPRead calls returning full source (~200 lines each), SAPContext returns ONE response with compressed contracts (~15-30 lines each). Typical compression: 7-30x fewer tokens. What gets extracted per dependency: - Classes: CLASS DEFINITION with PUBLIC SECTION only (methods, types, constants). PROTECTED, PRIVATE and IMPLEMENTATION stripped. - Interfaces: Full interface definition (interfaces are already public contracts). - Function modules: FUNCTION signature block only (IMPORTING/EXPORTING parameters). Filtering: SAP standard objects (CL_ABAP_*, IF_ABAP_*, CX_SY_*) are excluded — the LLM already knows standard SAP APIs. Custom objects (Z*, Y*) are prioritized. Use SAPContext BEFORE writing code that modifies or extends existing objects. Use SAPRead to get the full source of the target object, then SAPContext to understand its dependencies.. It is categorised as a Read tool in the Arc 1 MCP Server, which means it retrieves data without modifying state.
Register the Arc 1 MCP server in PolicyLayer and add a rule for SAPContext: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Arc 1. Nothing to install.
SAPContext is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the SAPContext rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for SAPContext. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
SAPContext is provided by the Arc 1 MCP server (marianfoo/arc-1). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 11 Arc 1 tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.